mihirp1998 / AlignProp
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
☆256Updated 2 months ago
Alternatives and similar repositories for AlignProp:
Users that are interested in AlignProp are comparing it to the libraries listed below
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆317Updated 2 weeks ago
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆329Updated 4 months ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆187Updated 9 months ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆284Updated 3 months ago
- GenEval: An object-focused framework for evaluating text-to-image alignment☆153Updated 6 months ago
- [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation☆229Updated this week
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆116Updated this week
- MoVQGAN - model for the image encoding and reconstruction☆215Updated last year
- [WACV 2024] Training-Free Layout Control with Cross-Attention Guidance☆245Updated 10 months ago
- SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training☆165Updated this week
- Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆173Updated last month
- An in-context conditioning version of MUSE with pre-trained checkpoints.☆111Updated last year
- Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.☆306Updated 6 months ago
- (CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision☆118Updated last month
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆229Updated 5 months ago
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆440Updated 8 months ago
- 🚀 Cross attention map tools for huggingface/diffusers☆207Updated last week
- 🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)☆164Updated 9 months ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆272Updated last year
- Implementation of "DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning"☆82Updated last year
- [CVPR 2024] Official implementation of CVPR 2024 paper: "Inversion-Free Image Editing with Natural Language"☆305Updated 8 months ago
- [CVPR 2024] | LAMP: Learn a Motion Pattern for Few-Shot Based Video Generation☆274Updated 9 months ago
- [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy☆239Updated last month
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆381Updated last year
- ☆163Updated last year
- [NeurIPS 2023 Spotlight] Real-World Image Variation by Aligning Diffusion Inversion Chain☆148Updated last year
- [ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need☆165Updated last month
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆395Updated 2 months ago
- ☆468Updated last month
- My Implementation of Adversarial Diffusion Distillation https://arxiv.org/pdf/2311.17042.pdf☆60Updated last month